English
Related papers

Related papers: Uncertainty-Guided Inference-Time Depth Adaptation…

200 papers

Transfer learning based on full fine-tuning (FFT) of the pre-trained encoder and task-specific decoder becomes increasingly complex as deep models grow exponentially. Parameter efficient fine-tuning (PEFT) approaches using adapters…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Hayeon Jo , Hyesong Choi , Minhee Cho , Dongbo Min

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Fengyuan Shi , Ruopeng Gao , Weilin Huang , Limin Wang

Vision-based target tracking is crucial for unmanned surface vehicles (USVs) to perform tasks such as inspection, monitoring, and surveillance. However, real-time tracking in complex maritime environments is challenging due to dynamic…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Muhayy Ud Din , Ahsan B. Bakht , Waseem Akram , Yihao Dong , Lakmal Seneviratne , Irfan Hussain

The high energy physics unfolding problem is an important statistical inverse problem in data analysis at the Large Hadron Collider (LHC) at CERN. The goal of unfolding is to make nonparametric inferences about a particle spectrum from…

Applications · Statistics 2017-06-09 Mikael Kuusela , Philip B. Stark

Deep learning-based video compression is a challenging task, and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Wufei Ma , Jiahao Li , Bin Li , Yan Lu

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Mingzhe Guo , Zhipeng Zhang , Heng Fan , Liping Jing

We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture. It is a modified version of TransTrack, which overcomes the computational…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Siddharth Sagar Nijhawan , Leo Hoshikawa , Atsushi Irie , Masakazu Yoshimura , Junji Otsuka , Takeshi Ohashi

Visual object tracking (VOT) plays a pivotal role in unmanned aerial vehicle (UAV) applications. Addressing the trade-off between accuracy and efficiency, especially under challenging conditions like unpredictable occlusion, remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Yang Zhou , Derui Ding , Ran Sun , Ying Sun , Haohua Zhang

We propose ProTracker, a novel framework for accurate and robust long-term dense tracking of arbitrary points in videos. Previous methods relying on global cost volumes effectively handle large occlusions and scene changes but lack…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Tingyang Zhang , Chen Wang , Zhiyang Dou , Qingzhe Gao , Jiahui Lei , Baoquan Chen , Lingjie Liu

Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector input sizes causes small target features to collapse below…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jiawen Wen , Yu Hu , Suixuan Qiu , Jinshan Huang , Xiaowen Chu

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with…

Computation and Language · Computer Science 2021-11-04 Pu-Chin Chen , Henry Tsai , Srinadh Bhojanapalli , Hyung Won Chung , Yin-Wen Chang , Chun-Sung Ferng

Depth estimation plays a crucial role in various tasks within endoscopic surgery, including navigation, surface reconstruction, and augmented reality visualization. Despite the significant achievements of foundation models in vision tasks,…

Image and Video Processing · Electrical Eng. & Systems 2024-05-15 Beilei Cui , Mobarakol Islam , Long Bai , An Wang , Hongliang Ren

In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Hongyang Li , Hao Zhang , Shilong Liu , Zhaoyang Zeng , Tianhe Ren , Feng Li , Lei Zhang

Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking the real-world conditions; 2) adopt the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Ziang Cao , Ziyuan Huang , Liang Pan , Shiwei Zhang , Ziwei Liu , Changhong Fu

Hyperspectral imagery encodes rich material properties that can improve tracking robustness under appearance ambiguity, illumination change, and background clutter. However, due to the limited availability of hyperspectral video data, many…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Xu Han , Mohammad Aminul Islam , Lei Wang , Zekun Long , Guanmanyi Fu , Wangshu Cai , Kuldip K. Paliwal , Jun Zhou

Next-generation wireless networks are expected to leverage multi-modal data sources to execute various wireless communication tasks such as beamforming and blockage prediction with situational-awareness. To do so, multi-modal transformers…

Systems and Control · Electrical Eng. & Systems 2026-04-22 Minsu Kim , Walid Saad , Kui Wang , Zongdian Li , Tao Yu , Kei Sakaguchi

Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In contrast, traditional video codecs employ a flexible encoder…

Image and Video Processing · Electrical Eng. & Systems 2024-04-23 Xingtong Ge , Jixiang Luo , Xinjie Zhang , Tongda Xu , Guo Lu , Dailan He , Jing Geng , Yan Wang , Jun Zhang , Hongwei Qin

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…

Machine Learning · Computer Science 2026-05-27 Youngin Kim , Ray Sun , Inho Kim , Bumsoo Park , Hyun Oh Song

Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N, and RGB+D)…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Lingyi Hong , Shilin Yan , Renrui Zhang , Wanyun Li , Xinyu Zhou , Pinxue Guo , Kaixun Jiang , Yiting Chen , Jinglun Li , Zhaoyu Chen , Wenqiang Zhang

Accurate object tracking in low-light environments is crucial, particularly in surveillance and ethology applications. However, achieving this is significantly challenging due to the poor quality of captured sequences. Factors such as…

Computer Vision and Pattern Recognition · Computer Science 2024-01-04 Anqi Yi , Nantheera Anantrasirichai
‹ Prev 1 8 9 10 Next ›